Learning Multiagent Communication with Backpropagation

By Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus. 2016

1,366 citations recorded by the source corpus.

Many tasks in AI require the collaboration of multiple agents. Typically, the communication protocol between agents is manually specified and not altered during training. In this paper we explore a simple neural model, called CommNet, that uses continuous communication for fully cooperative tasks. The model consists of multiple agents and the communication between them is learned alongside their policy. We apply this model to a diverse set of tasks, demonstrating the ability of the agents to learn to communicate amongst themselves, yielding improved performance over non-communicative agents and baselines. In some cases, it is possible to interpret the language devised by the agents, revealing simple but effective strategies for solving the task at hand.

Subfields: Artificial Intelligence, Natural Language Processing, LLM Agents & Tool Use

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yoshua Bengio
  2. Sergey Levine
  3. Mohit Bansal
  4. Jianfeng Gao
  5. Ruslan Salakhutdinov
  6. Quoc V. Le
  7. Percy Liang
  8. Kyunghyun Cho

In Natural Language Processing

  1. Mohit Bansal
  2. Kyunghyun Cho
  3. Jianfeng Gao
  4. Jason Aaron Edward Weston
  5. Yejin Choi
  6. Yoshua Bengio
  7. Christopher D. Manning
  8. Richard Socher

In LLM Agents & Tool Use

  1. Shimon Whiteson
  2. Zongqing Lu
  3. Chongjie Zhang
  4. Jiechuan Jiang
  5. Stefano V. Albrecht
  6. Filippos Christianos
  7. Richard Ryan Williams
  8. Igor Mordatch

Citations in the corpus